OpenHermes 2.5 Mistral 7B

teknium/openhermes-2.5-mistral-7b

Created Nov 20, 20234,096 context

A continuation of OpenHermes 2 model, trained on additional code datasets. Potentially the most interesting finding from training on a good ratio (est. of around 7-14% of the total dataset) of code instruction was that it has boosted several non-code benchmarks, including TruthfulQA, AGIEval, and GPT4All suite. It did however reduce BigBench benchmark score, but the net gain overall is significant.

Recent activity on OpenHermes 2.5 Mistral 7B

Tokens processed per day

More models from Teknium

OpenHermes 2 Mistral 7B

Trained on 900k instructions, surpasses all previous versions of Hermes 13B and below, and matches 70B on some benchmarks. Hermes 2 has strong multiturn chat skills and system prompt capabilities.